GRU-ODE and GRU-Bayes have complementary

We thank reviewers for the relevant comments. We first address general questions and then give brief individual answers. Those projected distributions vary smoothly as they are driven by an ODE. Continuous-time Bayesian networks (Nodelman et al., UAI 2002) address a This joint modeling of continuous measurements and events was left for future work. Some assumptions have to be made about the conditional distribution of the observations.